An Integrated Deep Generative Model for Text Classification and Generation
Text classification and generation are two important tasks in the field of natural language processing. In this paper, we deal with both tasks via Variational Autoencoder, which is a powerful deep generative model. The self-attention mechanism is introduced to the encoder. The modified encoder extra...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Hindawi Limited
2018-01-01
|
| Series: | Mathematical Problems in Engineering |
| Online Access: | http://dx.doi.org/10.1155/2018/7529286 |
| Summary: | Text classification and generation are two important tasks in the field of natural language processing. In this paper, we deal with both tasks via Variational Autoencoder, which is a powerful deep generative model. The self-attention mechanism is introduced to the encoder. The modified encoder extracts the global feature of the input text to produce the hidden code, and we train a neural network classifier based on the hidden code to perform the classification. On the other hand, the label of the text is fed into the decoder explicitly to enhance the categorization information, which could help with text generation. The experiments have shown that our model could achieve competitive classification results and the generated text is realistic. Thus the proposed integrated deep generative model could be an alternative for both tasks. |
|---|---|
| ISSN: | 1024-123X 1563-5147 |